AI model · OpenAI
gpt-oss-120b (batch)
Model ID: openai/gpt-oss-120b:batch
- Input
- $0.03 per 1M tokens
- Output
- $0.14 per 1M tokens
- Context
- 131K tokens at once
- Max output
- 118K tokens per reply
- Released
- 5 Aug 2025 OpenAI
What it can do
- YesReasoning
- YesTool calling
- NoImage input
- YesOpen weights
- NoFree to use
Takes text; gives text.
How its listing describes it
gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...
Sources
- OpenAI: gpt-oss-120b (batch) on OpenRouter — read 2 Oct 2026